© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1362
    Prev
    Next
    INDEX
    Explanations

    specific dates or mentions of time in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    edom
    -0.06
    crast
    -0.06
    dal
    -0.06
    sel
    -0.06
    peed
    -0.06
    dar
    -0.05
     len
    -0.05
    esel
    -0.05
     Wend
    -0.05
    .loads
    -0.05
    POSITIVE LOGITS
    acs
    0.07
    ä»ģ
    0.07
     Ñĩа
    0.07
     GetType
    0.07
     ÑģмоÑĤ
    0.07
    γει
    0.07
    ãģ°ãģĭãĤĬ
    0.06
     Hath
    0.06
    (strtolower
    0.06
    ç´
    0.06
    Activations Density 0.022%

    No Known Activations